Giovanni: Agent for Claude Code

.claude/agents/README.md

README is an agent for Claude Code from jaroslavsoucek-art/Giovanni. It costs 0 tokens per session (1,654 once invoked), scanned A, original, MIT.

A collection of custom helper agents for Giovanni, each stored as a Markdown file and started through the Agent tool or slash commands. Some create project structures, while others perform recurring operational tasks.

In plain words
What is it for?
Pulling information from sources such as email, calendars, project trackers, version control, customer systems, and documents.
Why use it?
It documents which helper agents exist and when to use them, so work can be divided consistently.

Agent for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths; mentions subagents.

This is jaroslavsoucek-art/Giovanni's own configuration. It tells Claude Code how to work on Giovanni itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Giovanni configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jaroslavsoucek-art/Giovanni. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jaroslavsoucek-art/Giovanni/main/.claude/agents/README.md
Clone the repo
git clone --depth 1 https://github.com/jaroslavsoucek-art/Giovanni

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for README

README.md
[![agentmods](https://agentmods.dev/badge/agents/jaroslavsoucek-art/giovanni/readme/github.svg)](https://agentmods.dev/agents/jaroslavsoucek-art/giovanni/readme)
Your own site
<a href="https://agentmods.dev/agents/jaroslavsoucek-art/giovanni/readme"><img src="https://agentmods.dev/badge/agents/jaroslavsoucek-art/giovanni/readme/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for README

Your own site · 80×15
<a href="https://agentmods.dev/agents/jaroslavsoucek-art/giovanni/readme"><img src="https://agentmods.dev/badge/agents/jaroslavsoucek-art/giovanni/readme.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,654 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01654
Opus 5 $0.00000 $0.00827
Sonnet 5 $0.00000 $0.00331
Haiku 4.5 $0.00000 $0.00165

Measured 9d ago against content hash c01ee115fbe8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

README scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/README.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents

Custom subagents for Giovanni. Each lives at .claude/agents/<name>.md and is spawned via the Agent tool (or via slash commands that route through prediction-runtime).

Two populations live in this directory:

  1. Architect agents — framework-builders. Spawned during Giovanni bootstrap to produce templates / docs / scripts. Frozen after bootstrap — they don't run in daily operations. (memory-architect, governance-architect, stakeholder-architect, prediction-architect, subagent-roster-architect, adversarial-architect, digest-architect, slash-command-architect)

  2. Operational agents — worker agents. Spawned by the fork's user during daily operations. This is what the rest of this README is about.

Design philosophy + invocation patterns: see docs/agents.md.

Operational agent roster

Agent One-liner Model When to spawn
source-puller Pull a single source (chat / email / calendar / project tracker / version control / CRM / docs) for a time window — return structured bullets, no synthesis sonnet Parallel fan-out in daily digest workflows; any time you need raw signal from one source isolated from main thread context
researcher External research via web search + fetch — return structured memory note (FACT / ANALOGY / ESTIMATE) + optional constitution patch proposal opus "Investigate X", "research X", "verify claim about Y" — anything requiring sources outside the repo
profile-bootstrap Bootstrap a new stakeholder profile OR refresh an existing one in memory/stakeholders/<slug>.md opus "Bootstrap stakeholder X", "refresh profile X", "who is X" (when not yet profiled)
deliverable-reviewer Pre-share content QA pass — consistency, diff vs prior, provenance, voice match. SHIP / REWRITE / KILL verdict. Read-only. opus After writing any deliverable in deliverables/; before sharing externally
consistency-checker Semantic drift checks across memory + constitution + agent roster + decision records. Surfaces contradictions that deterministic lint can't catch. sonnet Via /consistency-check slash command — NOT auto. Cadence is configurable per fork.
market-radar Proactive external competitive / market intelligence scan. Default = periodic sweep; focused = topic / market / competitor deep-dive opus Via /market-radar slash command. Manual cadence; weekly default.
prediction-runtime Executes /branch-out (active simulation), /shadow-review (quarterly verdict pass), /calibration-report (monthly aggregation). Carries the 8 binding principles. opus Via slash commands — never invoked directly by user.
adversarial-reviewer Adversarial review of strategic drafts — SHIP / REWRITE / KILL verdict with strongest counter-case construction. Default-critical mode, no flattery. opus Via /review or /redline slash commands; or when draft contains [REVIEW] tag or message starts with review: / redline: / before send:

Read the full file on GitHub · 87 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 87 lines · 0 tokens per session scan A c01ee115fbe8

Subscribe to this mod's changes

README is an agent published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,654 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

data-engineer

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.

wshobson/agents · 54 tokens

reviewer

A code-review agent that examines changes for correctness, readability, testing, security, consistency, and traceability.

Insajin/autopus-adk · 42 tokens

solid-open-closed-judge

Evaluates code implementation adherence to SOLID Open/Closed Principle (OCP).

closedloop-ai/claude-plugins · 23 tokens

architect

An architecture agent that studies a system and records decisions about its structure, interfaces, dependencies, and future changes.

Insajin/autopus-adk · 39 tokens

design-builder

Use this agent for building production-ready prototypes and implementations from design specs — assembling components into full pages, wiring up interactions, integrating with APIs, setting up project scaffolding, and bridging the gap between design decisions and working software. Dispatch after the design-lead has…

Owl-Listener/designpowers · 85 tokens

inspiration-scout

Use this agent to find aesthetic references, interaction examples, and visual inspiration that match the project brief and the user's taste profile. Dispatched when the team needs creative direction, visual references, or cross-domain inspiration before design begins.

Owl-Listener/designpowers · 50 tokens